Enhancing Small Object Detection from UAV Perspectives via an Improved YOLOv11 Model

Authors

  • Yue Hong
  • Byung-Won Min
  • Shentao Wang
  • Yuxiao Hu

DOI:

https://doi.org/10.6919/ICJE.202507_11(7).0001

Keywords:

YOLOv11; Object Detection; UAV Perspective; Aerial Imagery; Small Object Detection.

Abstract

Object detection in UAV aerial imagery faces significant challenges, including a high proportion of small objects, large viewpoint variations, severe occlusions in dense scenes, and difficulties in low-light or nighttime conditions. To address these issues, this paper proposes an improved version of YOLOv11 by incorporating a Partial Convolution (PConv) mechanism, which enhances the model’s sensitivity to edge regions and sparse salient targets. Additionally, a Spatial and Channel Self-Attention (SCSA) module is introduced to improve feature focusing by jointly modeling spatial and channel-wise dependencies. Together, these enhancements form the YOLOv11-PCSCSA model, which achieves a lightweight structure and precise perception capabilities. Experiments conducted on two benchmark UAV datasets, HIT-UAV and VisDrone2019, demonstrate that the proposed model outperforms the original YOLOv11 in terms of both mAP@0.5 and mAP@0.95 metrics.

Downloads

Download data is not yet available.

References

[1] Xue Z, Xu R, Bai D, et al. YOLO-tea: A tea disease detection model improved by YOLOv5[J]. Forests, 2023, 14(2): 415.

[2] Zhou X, Xu X, Liang W, et al. Intelligent small object detection for digital twin in smart manufacturing with industrial cyber-physical systems[J]. IEEE Transactions on Industrial Informatics, 2021, 18(2): 1377-1386.

[3] Guo Y, Chen S, Zhan R, et al. LMSD-YOLO: A lightweight YOLO algorithm for multi-scale SAR ship detection[J]. Remote Sensing, 2022, 14(19): 4801.

[4] Yuan M, Zhou Y, Ren X, et al. YOLO-HMC: An improved method for PCB surface defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 1-11.

[5] Bi H, Feng Y, Tong B, et al. RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation[J]. arXiv preprint arXiv:2504.03166, 2025.

[6] Yu C, Jiang X, Wu F, et al. Research on Vehicle Detection in Infrared Aerial Images in Complex Urban and Road Backgrounds[J]. Electronics, 2024, 13(2): 319.

[7] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C] Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.

[8] RedmonJ, Farhadi A.Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018.

[9] Bochkovskiy A, Wang C Y, Liao H Y M. Yolov4: Optimal speed and accuracy of object detection[J]. arXiv preprint arXiv:2004.10934, 2020.

[10] Wang C Y, Bochkovskiy A, Liao H Y M. Scaled-yolov4: Scaling cross stage partial network[C]//Proceedings of the IEEE/cvf conference on computer vision and pattern recognition. 2021: 13029-13038.

[11] Li C, Li L, Jiang H, et al. YOLOv6: A single-stage object detection framework for industrial applications[J]. arXiv preprint arXiv:2209.02976, 2022.

[12] Li C, Li L, Geng Y, et al. Yolov6 v3.0: A full-scale reloading[J].arXiv preprint arXiv:2301.05586, 2023.

[13] Wang CY, BochkovskiyA, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state- of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 7464-7475.

[14] Huang X, Wang X, Lv W, et al. PP-YOLOv2: A practical object detector[J]. arXiv preprint arXiv:2104.10419, 2021.

[15] Xu S, Wang X, Lv W, et al. PP-YOLOE: An evolved version of YOLO[J]. arXiv preprint arXiv:2203.16250, 2022.

[16] Wang C Y, Yeh I H, Liao H Y M. YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information[J]. arXiv preprint arXiv:2402.13616, 2024.

[17] Chen, J.; Kao, S.h.; He, H.; Zhuo, W.; Wen, S.; Lee, C.H.; Chan, S.H.G. Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 17–24 June 2023; pp. 12021–12031.

[18] Chen J, Kao S, He H, et al. Run, don't walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023: 12021-12031.

[19] Suo J, Wang T, Zhang X, et al. HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection[J]. Scientific Data, 2023, 10(1): 227.

[20] Du D, Zhu P, Wen L, et al. VisDrone-DET2019: The vision meets drone object detection in image challenge results[C]//Proceedings of the IEEE/CVF international conference on computer vision workshops. 2019: 0-0.

Downloads

Published

2025-06-27

Issue

Section

Articles

How to Cite

Hong, Y., Byung-Won Min, Wang, S., & Hu, Y. (2025). Enhancing Small Object Detection from UAV Perspectives via an Improved YOLOv11 Model. International Core Journal of Engineering, 11(7), 1-8. https://doi.org/10.6919/ICJE.202507_11(7).0001